Abstract
Superquadrics are one of the ideal shape representations for adapting various kinds of primitive shapes with a single equation. This paper revisits the task of representing a 3D human body with multiple superquadrics. As a single superquadric surface can only represent symmetric primitive shapes, we present a method that segments the human body into body parts to estimate their superquadric parameters. Moreover, we propose a novel initial parameter estimation method by using 3D skeleton joints. The results show that superquadric parameters are estimated, which represent human body parts volumetrically.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abelha, P., Guerin, F.: Learning how a tool affords by simulating 3D models from the web. In: IEEE/RSJ IROS, pp. 4923–4929, September 2017
Afanasyev, I., et al.: 3D human body pose estimation by superquadrics. In: VISAPP, vol. 2, January 2012
Bardinet, E., Cohen, L.D., Ayache, N.: A parametric deformable model to fit unstructured 3D data. Comput. Vis. Image Underst. 71(1), 39–54 (1998)
Barr, A.H.: Superquadrics and angle-preserving transformations. IEEE Comput. Graph. Appl. 1(1), 11–23 (1981)
Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)
Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., Yuille, A.L.: Detect what you can: detecting and representing objects using holistic models and body parts. In: CVPR, pp. 1979–1986 (2014)
Drews Jr., P., Trujillo, P.N., Rocha, R.P., Campos, M.F.M., Dias, J.: Novelty detection and 3D shape retrieval using superquadrics and multi-scale sampling for autonomous mobile robots. In: ICRA, pp. 3635–3640 (2010)
Duncan, K., Sarkar, S., Alqasemi, R., Dubey, R.: Multi-scale superquadric fitting for efficient shape and pose recovery of unknown objects. In: ICRA, pp. 4238–4243 (2013)
Krivic, J., Solina, F.: Part-level object recognition using superquadrics. CVIU 95(1), 105–126 (2004)
Shi, L., Cheng, I., Basu, A.: Anatomy preserving 3D model decomposition based on robust skeleton-surface node correspondence. In: International Conference on Multimedia and Expo, pp. 1–6, July 2011
Mehta, D., et al.: VNect: real-time 3D human pose estimation with a single RGB camera, vol. 36 (2017). http://gvv.mpi-inf.mpg.de/projects/VNect/
Moré, J.J.: The Levenberg-Marquardt algorithm: Implementation and theory. In: Watson, G.A. (ed.) Numerical Analysis. LNM, vol. 630, pp. 105–116. Springer, Heidelberg (1978). https://doi.org/10.1007/BFb0067700
Lee, M.W., Cohen, I.: A model-based approach for estimating human 3D poses in static images. Trans. Pattern Anal. Mach. Intell. 28(6), 905–916 (2006)
Nekrasov, V., Shen, C., Reid, I.D.: Light-weight refinenet for real-time semantic segmentation. In: BMVC (2018)
Paschalidou, D., Ulusoy, A.O., Geiger, A.: Superquadrics revisited: learning 3D shape parsing beyond cuboids. In: CVPR (2019)
Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. In: CVPR, pp. 1297–1304, June 2011
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, NIPS 2014, vol. 1, pp. 568–576 (2014)
Solina, F., Bajcsy, R.: Range image interpretation of mail pieces with superquadrics. In: AAAI, pp. 733–737 (1987)
Sundaresan, A., Chellappa, R.: Model driven segmentation of articulating humans in laplacian eigenspace. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1771–85 (2008)
Vaskevicius, N., Birk, A.: Revisiting superquadric fitting: a numerically stable formulation. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 220–233 (2019)
Acknowledgement
This work was supported by AIP-PRISM, Japan Science and Technology Agency, Grant Number JPMJCR18Y2, Japan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Hachiuma, R., Saito, H. (2019). Volumetric Representation of Semantically Segmented Human Body Parts Using Superquadrics. In: Bourdot, P., Interrante, V., Nedel, L., Magnenat-Thalmann, N., Zachmann, G. (eds) Virtual Reality and Augmented Reality. EuroVR 2019. Lecture Notes in Computer Science(), vol 11883. Springer, Cham. https://doi.org/10.1007/978-3-030-31908-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-31908-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31907-6
Online ISBN: 978-3-030-31908-3
eBook Packages: Computer ScienceComputer Science (R0)